Model comparison
Gemini 2.0 Flash-Lite vs GPT-4 Turbo
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.3 to 30.3 on the Noometry Index.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 9 categories and GPT-4 Turbo in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash-Lite leads 31.8 to 8.6.
- The biggest single-benchmark swing is DTBench: 52.5% for Gemini 2.0 Flash-Lite and 61.6% for GPT-4 Turbo.
Side by side
| Gemini 2.0 Flash-Lite | GPT-4 Turbo | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.3 | 30.3 |
| Released | 2025-02-05 | 2023-11-06 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $10 |
| Output $ / M tokens | — | $30 |
| Results tracked | 32 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 37.4 (#181), GPT-4 Turbo: 33.4 (#247)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Coding | 1322 | 1268 |
| WeirdML | — | 18% |
| BigCodeBench Instruct | — | 48.2% |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | — | 58.2% |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash-Lite: —, GPT-4 Turbo: —
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | — | 36.7% |
Reasoning Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 21.2 (#203), GPT-4 Turbo: 14.9 (#311)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1251 |
| DTBench | 52.5% | 61.6% |
| ForecastBench | 57.1 | 59.4 |
| SimpleBench | — | 25.1% |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 50.1% | — |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 9.8% |
| Epoch Capabilities Index | — | 127.25 |
| LiveBench | 54.3% | — |
Math Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 31.8 (#192), GPT-4 Turbo: 8.6 (#316)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Math | 1309 | 1272 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| Omni-MATH | 37.4% | — |
| LiveBench Math | 58.1% | — |
| MATH Level 5 | — | 46.7% |
Knowledge Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 34.6 (#185), GPT-4 Turbo: 24.3 (#263)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Expert | 1305 | 1223 |
| GPQA Diamond | — | 46.6% |
| MMLU-Pro | 72% | — |
| Confabulations | — | 28.4% |
| GPQA (HELM) | 50% | — |
| MMLU | — | 81.3% |
Multimodal Too close to call
Gemini 2.0 Flash-Lite: 30.6 (#103), GPT-4 Turbo: 30.0 (#104)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | 1100 | 1090 |
Multilingual Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 46.2 (#156), GPT-4 Turbo: 40.7 (#211)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1323 | 1245 |
| LMArena Chinese | 1339 | 1242 |
| LMArena French | 1346 | 1275 |
| LMArena German | 1306 | 1259 |
| LMArena Japanese | 1302 | 1194 |
| LMArena Korean | 1325 | 1187 |
| LMArena Russian | 1328 | 1259 |
| LMArena Spanish | 1313 | 1260 |
Instruction Following Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 70.6 (#158), GPT-4 Turbo: 66.0 (#211)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1305 | 1250 |
| LiveBench Instruction Following | 78.3% | — |
| IFEval | 82.4% | — |
Long Context Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 40.1 (#155), GPT-4 Turbo: 38.0 (#200)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1321 | 1254 |
Writing & Preference Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 51.9 (#172), GPT-4 Turbo: 47.9 (#201)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1330 | 1272 |
| LMArena Creative Writing | 1319 | 1269 |
| LMArena Multi-Turn | 1307 | 1267 |
| WildBench | 79% | — |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than GPT-4 Turbo?
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.3 to 30.3 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or GPT-4 Turbo better for coding?
Gemini 2.0 Flash-Lite scores higher on coding benchmarks: 37.4 versus 33.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and GPT-4 Turbo share?
20 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and GPT-4 Turbo has 36.